conftrace_

tree-like attention

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

reasoning acceleration (1) decoding speedup (1) parallel decoding (1) reasoning model (1) inference optimization (1) computational efficiency (1) autoregressive generation (1) sequence generation (1)

Papers

Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence EMNLP 2025